Royal Institute of Technology (KTH), Stockholm, Sweden
Januray 9-12, 2005
Pattern recognition is the act of taking in raw data and taking
an action based on properties of the pattern. Recognizing visual patterns is a
crucial part of our lives: we recognize people when we talk to them, we
recognize our cup on the breakfast table, our car in a parking lot, and so on.
While this task is performed with great accuracy and apparent little effort by
humans, it is still unclear how this performance is achieved. This has
challenged the computer vision and machine learning research community to build
artiﬁcial systems able to reproduce the human performance. After 30 years of
intensive research, the challenge is still open.
Support Vector Machines (SVMs) are a new generation learning system based on
recent advances in statistical learning theory. SVMs deliver stateoftheart
performance in realworld applications such as text categorization, handwritten
character recognition, image classiﬁcation, biosequence analysis, and so on.
Their ﬁrst introduction in the early 90s led to an explosion of applications and
deepening theoretical analysis, that has now established SVMs as one of the
standard tools for machine learning.
The goal of the course is to enable interested researchers and students to use
SVMs and SVMbased algorithms for stateoftheart visual application. I will not
assume any prior knowledge on SVMs and or visual pattern recognition, but I will
assume knowledge of probability theory.
|Time and Date:||�Sunday,
Jan 9, 2005���� 10:00-12:00 |
�Monday, Jan 10, 2005��� 13:00-15:00
�Tuesday, Jan 11, 2005�� 13:00-15:00
�Wednesday, Jan 12, 2005 14:00-15:45
|Place:||School of Mathematics, Niavaran Bldg., Niavaran Square, Tehran, Iran.